logistics/test.ipynb at b6ee600e78eb246c642ad94e4ab1b998f73ac5ac

4.4 MiB

Raw Blame History

In [ ]:

from utils.gtools import MySQLconnect
import pandas as pd
import numpy as np

In [ ]:

import tqdm
from utils.gtools import MySQLconnect
import pandas as pd
import numpy as np
import pickle
import os
# 读取csv文件
csv_file  = r"F:\DOCUMENTS\WXWork\1688854527635889\Cache\File\2025-03\Litfad产品点击数据 (26).csv"
print("读取csv文件...")
df1 = pd.read_csv(csv_file, skiprows=2)
max_len = len(df1)
batch_size = 500000
df1 = df1.rename(columns={"产品 ID": "psid"})
print("csv文件读取完毕")
for j in range(0, (max_len // batch_size) + 1):
    print(f"正在处理第{j}批数据...")
    start_idx = j * batch_size
    end_idx = start_idx + batch_size
    
    batch_df = df1.iloc[start_idx:end_idx]  # 获取每一批数据

    with MySQLconnect("ods") as db:
        conn = db.connect()
        cursor = conn.cursor()
        if not os.path.exists(f"spu_data{j}.csv"):
            for i,row in batch_df.iterrows():
                psid = row["psid"].split("sku")[1] if "sku" in row["psid"] else row["psid"]  # 产品PSID
                show_count = row["展示次数"]
                click_count = row["点击次数"]
                sql = rf"""SELECT SPU,DATE_FORMAT(spu.添加时间, '%Y-%m') AS 年月
                        FROM stg_bayshop_litfad_sku sku
                        left JOIN stg_bayshop_litfad_spu spu ON sku.`产品PID` =spu.`产品PID`
                        WHERE `产品PSID`  = '{psid}' 
                        """
                cursor.execute(sql)
                result = cursor.fetchone()
                if result:
                    year_month = result[0]
                    spu = result[1]
                else:
                    continue
                # df1新增一列保存这个年月
                batch_df.loc[i,"年月"] = year_month
                batch_df.loc[i,"SPU"] = spu
            batch_df.to_csv(f"spu_data{j}.csv", index=False, encoding="utf-8-sig")
        else:
            batch_df = pd.read_csv(f"spu_data{j}.csv")
    batch_df["展示次数"] = pd.to_numeric(batch_df["展示次数"], errors='coerce')
    batch_df["点击次数"] = pd.to_numeric(batch_df["点击次数"], errors='coerce')
    result1 = batch_df.groupby("年月").agg(
        年月 = ("年月", "first"),
        SPU = ("SPU", "first"),
        展示总次数 = ("展示次数", "sum"),
        点击总次数 = ("点击次数", "sum"))


    result = result1.groupby("SPU").agg(
                展示大于0点击为0数量=("年月", lambda x: ((result1.loc[x.index, "展示总次数"] > 0) & (result1.loc[x.index, "点击总次数"] == 0)).sum()),
                点击大于0数量=("年月", lambda x: (result1.loc[x.index, "点击总次数"] > 0).sum()),
                展示为0数量=("年月", lambda x: (result1.loc[x.index, "展示总次数"] == 0).sum())
            ).reset_index()


    result.to_csv(f"spu_statistics{j}.csv", index=False, encoding="utf-8-sig")

# 最后读取所有批次的统计数据并合并（相加）
all_result = pd.DataFrame()
for j in range(0, (max_len // batch_size) + 1):
    result = pd.read_csv(f"spu_statistics{j}.csv")
    # 以年月为组，其他数据各批次相加
    if all_result.empty:
        all_result = result
    else:
        all_result = pd.merge(all_result, result, on="SPU", how="outer", suffixes=('', '_new'))
        all_result = all_result.groupby("SPU").sum().reset_index()
all_result.to_csv("all_spu_statistics.csv", index=False, encoding="utf-8-sig")

In [ ]:

from utils.gtools import MySQLconnect
import pandas as pd
df=pd.read_excel(r"F:\DOCUMENTS\WXWork\1688854527635889\Cache\File\2025-03\导出订单维护任务数据2025-3-20.xlsx",sheet_name="导出订单维护任务数据2025-3-20")
df['订单数量'] = df['订单数量'].astype(str)
df = df[df['订单数量'].str.len() > 0]
df['订单数量'] = df['订单数量'].astype(float)
df = df[df['订单数量']>0]
df=df[['erp sku','订单号']]

In [ ]:

with MySQLconnect("ods") as db:
    engine = db.engine()
    conn = db.connect()
    cursor = conn.cursor()
    df_group = df.groupby('erp sku')
    for sku, group in df_group:
        for index,row in group.iterrows():
            order_id_list = group["订单号"].tolist()
            param = ",".join(f"'{order_id}'" for order_id in order_id_list)
        sql = f"""
            SELECT
            SKU,
            sum(as_value_amount) AS 销售额,
            sum(product_num) AS 产品数量,
            count(order_id) AS 订单数量,
            date_format(MAX(order_date), '%%Y-%%m-%%d') AS 最后一次订单日期
            FROM
            dws.fact_order_product_list
            WHERE
            SKU = {sku}
            AND order_id not IN ({param})
            group by SKU
        """
        amount_df = pd.read_sql(sql, con=engine)
        if amount_df.empty:
            amount = 0
            product_num = 0
            order_num = 0
            last_order_date = None
        else:
            amount = amount_df["销售额"].values[0]
            product_num = amount_df["产品数量"].values[0]
            order_num = amount_df["订单数量"].values[0]
            last_order_date = amount_df["最后一次订单日期"].values[0]
        df.loc[df["erp sku"] == sku, "不含此次总销售额"] = amount
        df.loc[df["erp sku"] == sku, "产品数量"] = product_num
        df.loc[df["erp sku"] == sku, "订单数量"] = order_num
        df.loc[df["erp sku"] == sku, "最后一次订单日期"] = last_order_date
        print(f"{sku}的销售额为{amount}, 产品数量为{product_num}, 订单数量为{order_num}, 最后一次订单日期为{last_order_date}")

df = df.drop_duplicates(subset=["erp sku", "订单号"], keep="last")
df.to_clipboard(index=False)

In [ ]:

from utils.countryOperator import OperateCountry
from utils.logisticsBill import BillFactory
from utils.Package import Package, Package_group
import pandas as pd
from utils.gtools import MySQLconnect
# 美国 
from utils.logisticsBill import Billing
ods = MySQLconnect('ods')
cursor = ods.connect().cursor()
df = pd.read_excel(r'F:\DOCUMENTS\WXWork\1688854527635889\Cache\File\2025-04\Litfad 4-10-25 with data analysis-2(1).xlsx',
                   sheet_name='NJ-96004848')
df_grouped= df.groupby('TRACKING#')
calculated_results = []
package_list = ",".join(str(item) for item in df['ORDER#'].tolist())
print(package_list)
query = f"SELECT package,length,width,hight,weight FROM `package_vol_info` WHERE `package` IN ({package_list})"
result = cursor.execute(query)
packages_info = cursor.fetchall()
print(packages_info)
# 将df和result合并
new_df = pd.DataFrame(packages_info, columns=['package', 'length', 'width', 'hight', 'weight'])
df = df.merge(new_df, left_on='ORDER#', right_on='package')
df = df.drop(columns='package')


for order_num, group in df_grouped:
    # opCountry = OperateCountry(group['目的国'].iloc[0])
    opCountry = OperateCountry('US')
    postcode = group['ZIPCODE'].iloc[0]
    packages= Package_group()
    packages_dict = {}
    volume_weight = 0
    weight = 0
    for index,row in group.iterrows():
        length = float(row['L*H*W(CM)'].split('*')[0])
        width = float(row['L*H*W(CM)'].split('*')[1])
        hight = float(row['L*H*W(CM)'].split('*')[2])
        weight = row['WEIGHT']
        package = Package(row['ORDER#'],length,width,hight,weight)
        packages.add_package(package)
        # packages_dict[row['包裹号']] = {
        #     "长": row['长'],
        #     "宽": row['宽'],
        #     "高": row['高'],
        #     "重量": row['重量']
        # }
        # weight += row['重量']/1000
        # volume_weight += package.get_volume_weight(6000)
        # postcode = row['postcode']
        # head_type = 1 if row['运输方式'] == '海运' else 0
    try:
        bill1 = Billing(str(index),opCountry,packages,postcode,company_name='大健-Metro',head_type=1,beizhu='1')
        tail_price1 = bill1.tail_amount[0]
    except:
        tail_price1 = '出错'
    try:
        bill2 = Billing(str(index),opCountry,packages,postcode,company_name='大健-CEVA',head_type=1,beizhu='1')
        tail_price2 = bill2.tail_amount[0]
    except:
        tail_price2 = '出错'
    try:
        bill3 = Billing(str(index),opCountry,packages,postcode,company_name='大健-GIGA',head_type=1,beizhu='1')
        tail_price3 = bill3.tail_amount[0]
    except:
        tail_price3 = '出错'
    
    result = {
        'TRACKING#': order_num,
        '大健-MATRO': tail_price1,# Same for all rows in the group
        '大健-CEVA':tail_price2,
        '大健-GIGA':tail_price3,
    }
    print(result)
    calculated_results.append(result)
    # print(packages_dict)
calculated_df = pd.DataFrame(calculated_results)
# 将calculated_df的订单号改为order_id
# calculated_df.rename(columns={'订单号':'order_id'},inplace=True)
calculated_df

In [ ]:

# 取表格数据is_first为1的数据，取spu,长宽高重量系数
import pandas as pd
df = pd.read_excel(r'D:\test\logistics\拦截数据\一票一件发货订单.xlsx',sheet_name="单包裹系数计算")
# 写一个cal_size算法，输入原属性和新属性，返回涨幅系数
df=df[['is_first','SPU','SKU','长','宽','高','重量']]
base_df = df[df['is_first']==1]

In [ ]:

# 取这些SPU下的所有SKU及其现在售价
from sell.sell_price import call_sell_and_order_price
import json
from utils.gtools import MySQLconnect
import pandas as pd
spu_list = (
    base_df['SPU']
    .apply(pd.to_numeric, errors='coerce')  # 转数字，非法的变 NaN
    .dropna()
    .astype(int)
    .astype(str)
    .tolist()
)
placeholders = ','.join(['%s'] * len(spu_list)) 
# result = []
with MySQLconnect('ods') as db:
    enginal = db.engine()
    sql = f"""SELECT
    产品品类,
    产品分类,
        SPU,
        sku.SKU,
        sku.`成本价`,
        spi.`包裹数据`,
        物流分摊,
        产品售价
    FROM
        stg_bayshop_litfad_sku sku
        LEFT JOIN stg_bayshop_litfad_spu spu ON sku.`产品PID` = spu.`产品PID` 
        LEFT JOIN ads.new_erp_sku_size spi ON sku.SKU =spi.SKU
    WHERE
        spu.SPU IN ({placeholders}) 
        """
    result = pd.read_sql(sql, enginal,params= tuple(spu_list))
# 合并df
all_df = pd.merge(result,df, on=['SPU','SKU'], how='left')
all_df.head()

In [ ]:

# 先把ERP包裹数据拆出来
import re
import json
for index, row in all_df.iterrows():
    if not isinstance(row['包裹数据'], str) or not row['包裹数据']:
        print(f"第{index}行包裹数据为空或非字符串，跳过")
        continue
    try:
        package_dict = json.loads(row['包裹数据'])
    except json.JSONDecodeError as e:
        print(f"解析失败：第{index}行，错误信息：{e}")
        continue
    try:
        for package in package_dict.values():
            item = {}
            for key, value in package.items():
                try:
                    # 使用正则表达式提取数字部分
                    number_str = re.findall(r"[-+]?\d*\.\d+|\d+", str(value))
                    if number_str:
                        item[key] = float(number_str[0])  # 取第一个匹配到的数字并转换为 float
                    else:
                        item[key] = value  # 如果没有数字部分，保留原值
                except ValueError:
                    item[key] = value  # 如果遇到无法转换的值，保留原值
    except AttributeError:
        print(f"解析失败：第{index}行，错误信息：包裹数据为空")
        continue
    size = []
    size.append(item['长'])
    size.append(item['宽'])
    size.append(item['高'])
    weight = item['重量']
    size.sort()
    length = size[2]
    width = size[1]
    height = size[0]
    all_df.loc[index, 'ERP长'] = length
    all_df.loc[index, 'ERP宽'] = width
    all_df.loc[index, 'ERP高'] = height
    all_df.loc[index, 'ERP重量'] = weight
    print(f"{row['SKU']}尺寸为:{width},h:{height},d:{length},w:{weight}")

In [ ]:

# 计算每个SPU的长宽高重量系数
def cal_size(old,new):
    try:
        old = float(old)
        new = float(new)
        if old == 0:
            return None  # 或 return 0，防止除以0
        return (new - old) / old
    except (ValueError, TypeError):
        return None  # 遇到不能转为 float 的就返回 None
    
test_df = all_df[all_df['is_first']==1]
# 取基准数据SPU的系数
for index, row in test_df.iterrows():
    test_df.loc[index, '长系数'] = cal_size(row['ERP长'],row['长'])
    test_df.loc[index, '宽系数'] = cal_size(row['ERP宽'],row['宽'])
    test_df.loc[index, '高系数'] = cal_size(row['ERP高'],row['高'])
    test_df.loc[index, '重量系数'] = cal_size(row['ERP重量'],row['重量'])
    print(
        f"{row['SPU']} 的系数为 "
        f"{test_df.loc[index, '长系数']}, "
        f"{test_df.loc[index, '宽系数']}, "
        f"{test_df.loc[index, '高系数']}, "
        f"{test_df.loc[index, '重量系数']}"
    )
# 将SPU的基准系数合并至all_df
all_df = pd.merge(all_df, test_df[['SPU', '长系数', '宽系数', '高系数', '重量系数']], on='SPU', how='left')
all_df.to_excel('单包裹SKU售价分析.xlsx', index=False)

In [ ]:

import pandas as pd
all_df = pd.read_excel('单包裹SKU售价分析.xlsx')

# 根据系数 得到所有SKU的预测尺寸
# 根据系数计算每个SKU的理论尺寸
all_df['理论长'] = ((1 + all_df['长系数']) * all_df['ERP长']).round(2)
all_df['理论宽'] = ((1 + all_df['宽系数']) * all_df['ERP宽']).round(2)
all_df['理论高'] = ((1 + all_df['高系数']) * all_df['ERP高']).round(2)
all_df['理论重量'] = ((1 + all_df['重量系数']) * all_df['ERP重量']).round(2)

# 计算三种尺寸下的售价
# 计算预测后的尺寸下，一票一件订单的售价和订单价格
from sell.sell_price import call_sell_and_order_price
for index,row in all_df.iterrows():
    price = row['成本价']
    package_dict1={}
    package_dict2={}
    package_dict3={}
    try:
        package_dict1['包裹1'] = {}
        package_dict2['包裹1'] = {}
        package_dict3['包裹1'] = {}
        package_dict1['包裹1']['长'] = row['长']
        package_dict1['包裹1']['宽'] = row['宽']
        package_dict1['包裹1']['高'] = row['高']
        package_dict1['包裹1']['重量'] = row['重量']
        package_dict2['包裹1']['长'] = row['理论长']
        package_dict2['包裹1']['宽'] = row['理论宽']    
        package_dict2['包裹1']['高'] = row['理论高']
        package_dict2['包裹1']['重量'] = row['理论重量']
        package_dict3['包裹1']['长'] = row['ERP长']
        package_dict3['包裹1']['宽'] = row['ERP宽']    
        package_dict3['包裹1']['高'] = row['ERP高']
        package_dict3['包裹1']['重量'] = row['ERP重量']
        sell_price1, order_price1, order_type1 = call_sell_and_order_price(price, package_dict1)
        sell_price2, order_price2, order_type2 = call_sell_and_order_price(price, package_dict2)
        sell_price3, order_price3, order_type3 = call_sell_and_order_price(price, package_dict3)
    except Exception as e:
        print(f"SKU: {row['SKU']} 报错: {e}")
        continue
    all_df.loc[index, 'ERP售价'] = sell_price3
    all_df.loc[index, '实际体积售价'] = sell_price1
    all_df.loc[index, '理论体积售价'] = sell_price2

    all_df.loc[index, 'ERP订单价'] = order_price3
    all_df.loc[index, '实际体积订单价'] = order_price1
    all_df.loc[index, '理论体积订单价'] = order_price2
    # all_df.loc[index, '理论体积订单类型'] = order_type2
    print(f"SPU: {row['SPU']}, SKU {row['SKU']} ,网站售价: {row['产品售价']}, ERP售价: {sell_price3}, 实际体积售价: {sell_price1}, 理论体积售价: {sell_price2},")
all_df.to_excel('单包裹SKU售价分析.xlsx', index=False)

In [2]:

import pandas as pd
all_df = pd.read_excel('单包裹SKU售价分析1.xlsx',sheet_name="Sheet1")
all_df

Out[2]:

	产品品类	产品分类	SPU	SKU	成本价	包裹数据	物流分摊	产品售价	is_first	长	...	ERP订单价	理论体积订单价	最终售价选取	排除可能有误SPU	基准SKU是否已修改尺寸	最终售价修正	使用尺寸售价	是否有过修改记录
0	1 - Lighting	19 - Flush Mount Light	21267	22710	72.0	{"包裹1": {"宽": "46.0", "长": "46.00", "高": "13.0...	12.16	74.27	NaN	NaN	...	14.16	13.66	66.58	erp尺寸已修正，无需预测	是	68.22	ERP售价	否
1	1 - Lighting	19 - Flush Mount Light	21267	22711	72.0	{"包裹1": {"宽": "46.0", "长": "46.00", "高": "13.0...	12.16	74.27	NaN	NaN	...	14.16	13.66	66.58	erp尺寸已修正，无需预测	是	68.22	ERP售价	否
2	1 - Lighting	19 - Flush Mount Light	21267	22712	72.0	{"包裹1": {"宽": "46.0", "长": "46.00", "高": "13.0...	12.16	74.27	NaN	NaN	...	14.16	13.66	66.58	erp尺寸已修正，无需预测	是	68.22	ERP售价	否
3	1 - Lighting	19 - Flush Mount Light	21267	22713	72.0	{"包裹1": {"宽": "46.0", "长": "46.00", "高": "13.0...	12.16	74.27	NaN	NaN	...	14.16	13.66	66.58	erp尺寸已修正，无需预测	是	68.22	ERP售价	否
4	1 - Lighting	19 - Flush Mount Light	21267	22714	72.0	{"包裹1": {"宽": "46.0", "长": "46.00", "高": "13.0...	12.16	74.27	NaN	NaN	...	14.16	13.66	66.58	erp尺寸已修正，无需预测	是	68.22	ERP售价	否

5 rows × 38 columns

In [5]:

all_df = all_df[(all_df['是否有过修改记录']=="否")&(all_df['使用尺寸售价']!="ERP售价")]
all_df['SPU最大涨幅']=all_df.groupby('SPU')['售价涨跌幅'].transform(max)
all_df['SPU最小涨幅']=all_df.groupby('SPU')['售价涨跌幅'].transform(min)

filtered_df = all_df[(all_df['SPU最大涨幅'] <= 0.5) & (all_df['SPU最小涨幅'] >= -0.5)]
for index,row in filtered_df.iterrows():
    if row['使用尺寸售价']=="实际体积售价":
        length = str(row['长'])
        width = str(row['宽'])
        height = str(row['高'])
        weight = str(row['重量'])
    else:
        length = str(row['理论长'])
        width = str(row['理论宽'])
        height = str(row['理论高'])
        weight = str(row['理论重量'])
    filtered_df.loc[index, '尺寸重量'] = f"{weight}|{length}*{width}*{height}*1,"

    print(index)
spu_list = filtered_df['SPU'].unique()
filtered_df = filtered_df[['SKU','成本价','尺寸重量']]
filtered_df

C:\Users\Admin\AppData\Local\Temp\ipykernel_15708\615576954.py:2: FutureWarning: The provided callable <built-in function max> is currently using SeriesGroupBy.max. In a future version of pandas, the provided callable will be used directly. To keep current behavior pass the string "max" instead.
  all_df['SPU最大涨幅']=all_df.groupby('SPU')['售价涨跌幅'].transform(max)
C:\Users\Admin\AppData\Local\Temp\ipykernel_15708\615576954.py:3: FutureWarning: The provided callable <built-in function min> is currently using SeriesGroupBy.min. In a future version of pandas, the provided callable will be used directly. To keep current behavior pass the string "min" instead.
  all_df['SPU最小涨幅']=all_df.groupby('SPU')['售价涨跌幅'].transform(min)
C:\Users\Admin\AppData\Local\Temp\ipykernel_15708\615576954.py:17: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  filtered_df.loc[index, '尺寸重量'] = f"{weight}|{length}*{width}*{height}*1,"

Out[5]:

	SKU	成本价	尺寸重量
73	22789	23.0	579.31\|29.029.013.0*1,
74	22790	23.0	600.0\|29.029.013.0*1,
76	22792	23.0	600.0\|29.029.010.0*1,
77	22793	23.0	600.0\|29.029.013.0*1,
78	22794	23.0	729.31\|37.4637.4613.0*1,
...	...	...	...
559012	2207176438	617.0	23809.52\|193.040.021.94*1,
559037	2207192083	228.0	7000.0\|53.051.033.0*1,
559038	2207192084	228.0	7000.0\|53.051.033.0*1,
559039	2207192085	228.0	7000.0\|53.051.033.0*1,
559040	2207192086	228.0	7000.0\|53.051.033.0*1,

258790 rows × 3 columns

In [6]:

filtered_df.to_excel("product_property_data.xlsx")

In [ ]:

import pandas as pd
df=pd.read_clipboard()

Out[ ]:

	SPU	SKU	添加时间	产品分类	成本价	max_order_date	erp_package_vol	售卖金额	售卖数量	采购单价分段	网站售价	物流分摊费	头程cny	头程USD	订单物流费	尾端类型
0	21240931	225409012	2024/9/25 9:11:28	94 - Office Desks	153.4	2025/4/9 4:38:14	{"包裹1": {"宽": 65.0, "长": 85.0, "高": 25.0, "重量"...	140.99	1	200	187.650446	38.39	23.020833	23.020833	43.61	超长
1	21240931	225409014	2024/9/25 9:11:28	94 - Office Desks	153.4	2025/2/19 19:10:36	{"包裹1": {"宽": 65.0, "长": 85.0, "高": 25.0, "重量"...	141.00	1	200	187.650446	38.39	23.020833	23.020833	43.61	超长
2	21242537	225462586	2024/11/20 19:19:55	94 - Office Desks	183.0	2024/12/7 5:16:35	{"包裹1": {"宽": 60.0, "长": 130.0, "高": 8.0, "重量"...	115.77	1	200	156.120484	32.90	10.400000	10.400000	49.16	超长
3	21243430	225488100	2024/11/29 18:35:59	94 - Office Desks	98.0	2025/1/11 4:37:23	{"包裹1": {"宽": 48.0, "长": 63.0, "高": 10.0, "重量"...	187.32	3	100	79.745408	15.46	5.040000	5.040000	21.98	NaN
4	21243430	225488101	2024/11/29 18:35:59	94 - Office Desks	108.0	2024/12/8 3:11:38	{"包裹1": {"宽": 48.0, "长": 83.0, "高": 10.0, "重量"...	72.07	1	150	90.784690	16.45	6.640000	6.640000	23.69	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
7266	21848125	2206017140	2024/12/24 17:08:40	94 - Office Desks	199.0	2025/5/25 5:36:50	{"包裹1": {"宽": 68.0, "长": 108.0, "高": 10.0, "重量...	169.89	2	200	169.885215	32.90	12.240000	12.240000	49.16	超长
7267	21855006	2206091529	2024/12/30 19:54:42	94 - Office Desks	348.0	2024/12/31 6:17:53	{"包裹1": {"宽": 65.0, "长": 170.0, "高": 20.0, "重量...	368.82	1	350	438.130776	148.99	36.833333	36.833333	128.91	大包裹
7268	21855006	2206091531	2024/12/30 19:54:42	94 - Office Desks	389.0	2025/4/16 1:50:55	{"包裹1": {"宽": 65.0, "长": 110.0, "高": 20.0, "重量...	345.05	2	400	306.225895	38.75	23.833333	23.833333	55.64	超长
7269	21856565	2206109462	2024/12/30 20:19:29	94 - Office Desks	137.0	2025/1/1 1:31:22	{"包裹1": {"宽": 70.0, "长": 110.0, "高": 20.0, "重量...	143.74	1	150	194.917163	45.20	25.666667	25.666667	92.81	超长超重
7270	21857008	2206114147	2024/12/30 20:17:41	94 - Office Desks	428.0	2025/2/22 19:38:26	{"包裹1": {"宽": 60.0, "长": 130.0, "高": 25.0, "重量...	271.52	1	450	360.157538	45.69	32.500000	32.500000	94.47	超长超重

7271 rows × 16 columns

In [ ]:

D, E, F = [], [], []
temp_sum = 0

for i in range(len(df)):
    temp_sum += df.loc[i, '未售出']
    if df.loc[i, '已售出'] != 0:
        D.append(df.loc[i, '价格'])
        E.append(temp_sum)
        F.append(df.loc[i, '已售出'])
        temp_sum = 0  # 重置

# 结果
result = pd.DataFrame({'D': D, 'E': E, 'F': F})
result.to_clipboard(index=False)

4.4 MiB Raw Blame History Unescape Escape

4.4 MiB

Raw Blame History